#6935It has also successfully been coupled with rule-based and example based machine translation modules to build amulti engine machine translation system.
other,14-3-I05-2048,ak
new
<term>
language pairs
</term>
or new
<term>
domains
</term>
. This workshop is intended to give
#6805This is particularly important when building translation systems for new language pairs or newdomains.
tech,7-6-I05-2048,ak
tutorial will cover the basics of
<term>
SMT
</term>
: Theory will be put into practice
#6861The tutorial will cover the basics ofSMT:
tech,26-2-I05-2048,ak
</term>
gives competitive results to
<term>
rule-based translation systems
</term>
, requiring significantly less development
#6781Over the last few years dramatic improvements have been made, and a number of comparative evaluations have shown, that SMT gives competitive results torule-based translation systems, requiring significantly less development time.
tech,9-4-I05-2048,ak
intended to give an introduction to
<term>
statistical machine translation
</term>
with a focus on practical considerations
#6816This workshop is intended to give an introduction tostatistical machine translation with a focus on practical considerations.
tech,7-10-I05-2048,ak
also successfully been coupled with
<term>
rule-based and example based machine translation modules
</term>
to build a
<term>
multi engine machine
#6925It has also successfully been coupled withrule-based and example based machine translation modules to build a multi engine machine translation system.
tech,18-8-I05-2048,ak
introduced and used to build a working
<term>
translation system
</term>
.
<term>
STTK
</term>
has been developed
#6888STTK, a statistical machine translation tool kit, will be introduced and used to build a workingtranslation system.
tool,0-8-I05-2048,ak
Theory will be put into practice .
<term>
STTK
</term>
, a
<term>
statistical machine translation
#6870Theory will be put into practice.STTK, a statistical machine translation tool kit, will be introduced and used to build a working translation system.
tech,6-3-I05-2048,ak
particularly important when building
<term>
translation systems
</term>
for new
<term>
language pairs
</term>
#6797This is particularly important when buildingtranslation systems for new language pairs or new domains.
other,10-3-I05-2048,ak
<term>
translation systems
</term>
for new
<term>
language pairs
</term>
or new
<term>
domains
</term>
. This
#6801This is particularly important when building translation systems for newlanguage pairs or new domains.
tech,3-8-I05-2048,ak
into practice .
<term>
STTK
</term>
, a
<term>
statistical machine translation tool kit
</term>
, will be introduced and used to
#6873STTK, astatistical machine translation tool kit, will be introduced and used to build a working translation system.
other,21-5-I05-2048,ak
</term>
themselves and achieving good
<term>
baseline results
</term>
in a short time . The tutorial will
#6847Participants should be able, after attending this workshop, to set out building an SMT system themselves and achieving goodbaseline results in a short time.
tech,14-1-I05-2048,ak
currently one of the hot spots in
<term>
natural language processing
</term>
. Over the last few years dramatic
#6751Statistical machine translation (SMT) is currently one of the hot spots innatural language processing.
tool,0-9-I05-2048,ak
working
<term>
translation system
</term>
.
<term>
STTK
</term>
has been developed by the presenter
#6891STTK, a statistical machine translation tool kit, will be introduced and used to build a working translation system.STTK has been developed by the presenter and co-workers over a number of years and is currently used as the basis of CMU's SMT system.
tech,0-1-I05-2048,ak
dependency accuracy
</term>
by 10.08 % .
<term>
Statistical machine translation ( SMT )
</term>
is currently one of the hot spots
#6737In experimental evaluation, our proposed method outperforms previous shift-reduce dependency parsers for the Chine language, showing improvement of dependency accuracy by 10.08%.Statistical machine translation ( SMT ) is currently one of the hot spots in natural language processing.
tech,22-9-I05-2048,ak
is currently used as the basis of
<term>
CMU 's SMT system
</term>
. It has also successfully been coupled
#6913STTK has been developed by the presenter and co-workers over a number of years and is currently used as the basis ofCMU 's SMT system.
tech,15-5-I05-2048,ak
workshop , to set out building an
<term>
SMT system
</term>
themselves and achieving good
<term>
#6841Participants should be able, after attending this workshop, to set out building anSMT system themselves and achieving good baseline results in a short time.
tech,21-2-I05-2048,ak
comparative evaluations have shown , that
<term>
SMT
</term>
gives competitive results to
<term>
#6776Over the last few years dramatic improvements have been made, and a number of comparative evaluations have shown, thatSMT gives competitive results to rule-based translation systems, requiring significantly less development time.